Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Citrus vein phloem degeneration detection and classification method based on D-S theory through multi-source data fusion

A technology of citrus huanglongbing and multi-source data, applied in the field of detection and classification of citrus huanglongbing based on multi-source data fusion based on D-S theory, citrus huanglongbing detection and classification, can solve the problems of difficult observation, difficult to promote, and expensive electron microscope equipment

Active Publication Date: 2014-09-10
SOUTH CHINA AGRI UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage is that it takes a long time to diagnose the disease in time; the electron microscope observation method can use electron microscope, projection fluorescence microscope, optical microscope and other auxiliary equipment to observe specific disease symptoms, so as to determine the HLB pathogen
Because the concentration of HLB bacteria in citrus trees is low and the distribution is uneven, it is difficult to observe. In addition, the electron microscope equipment is expensive, which makes it difficult to promote in production.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Citrus vein phloem degeneration detection and classification method based on D-S theory through multi-source data fusion
  • Citrus vein phloem degeneration detection and classification method based on D-S theory through multi-source data fusion
  • Citrus vein phloem degeneration detection and classification method based on D-S theory through multi-source data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] like figure 1 As shown, the multi-source data fusion citrus Huanglongbing detection and classification method of the present embodiment comprises the following steps:

[0051] 1) Using the hyperspectral image acquisition platform, the visible spectrum image acquisition platform and the fluorescence spectrum image acquisition platform to collect the image information of the citrus leaf samples, classify the symptoms of Huanglongbing disease on the image information collected by each spectrum, and obtain each of the three spectrums. The recognition rate of similar symptoms, specifically:

[0052] The hyperspectral image acquisition platform such as figure 2 As shown, it includes a sample stage 1, an ultraviolet light source 2, a hyperspectral imager 3, a CCD camera 4 and a computer 5. Through the irradiation of the ultraviolet light source 2, the hyperspectral imager 3 and the CCD camera 4 are used to collect the citrus leaves on the sample stage 1. Sample image inform...

Embodiment 2

[0083] According to the method of Example 1 above, and for the convenience of testing, the classification of symptoms of Huanglongbing by hyperspectral, visible spectrum and fluorescence spectrum is uniformly divided into obvious symptoms, mild symptoms, zinc deficiency, healthy and yellowing, and obtain symptoms with obvious symptoms. For citrus leaf samples, the recognition rate obtained by each spectrum and the comprehensive recognition rate obtained by fusing the recognition rates of the three spectra are shown in Table 1 below.

[0084]

obvious symptoms

mild symptoms

Zinc deficiency

healthy

yellowing

Hyperspectral

0.9000

0

0

0.1000

0

visible spectrum

0.9000

0

0.1000

0

0

Fluorescence spectrum

0.8000

0

0.2000

0

0

fusion

0.998564

0.000000

0.001436

0.000000

0.000000

[0085] Table 1. Recognition rates of hyperspectral, visible and fl...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a citrus vein phloem degeneration detection and classification method based on the D-S theory through multi-source data fusion. The method includes utilizing a hyperspectral image collecting platform, a visible spectrum image collecting platform and a fluorescence spectra image collecting platform to collect image information of citrus leaf samples, performing classification of the symptoms of the citrus vein phloem degeneration on the various spectrum collected image information, and acquiring the identification rate of each classification of the symptoms of three varieties of spectrum; allowing the identification rates of three varieties of spectrum to serve as evidence sources, allocating PBA values to each proposition of an evidence identifying frame, and establishing credibility vectors of the evidence sources; allowing the credibility to serve as a discount factor to adjust the BPA values to each proposition of the evidence identifying frame; fusing the adjusted BPA values according to a Dempster combination rule, acquiring a comprehensive identification rate of the symptoms of the citrus vein phloem degeneration, and implementing correct diagnosis of the symptoms of the citrus vein phloem degeneration. According to the method, the identification rates of the hyperspectrum, visible spectrum and fluorescence spectra are fused, the comprehensive identification rate of the symptoms of the citrus vein phloem degeneration is acquired, and the correct diagnosis of the symptoms of the citrus vein phloem degeneration is implemented.

Description

technical field [0001] The invention relates to a detection and classification method for citrus Huanglongbing, in particular to a multi-source data fusion detection and classification method for citrus Huanglongbing based on D-S theory, and belongs to the field of citrus Huanglongbing detection. Background technique [0002] Citrus Huanglongbing (Liberobacter asiaticum) is a worldwide citrus disease. In my country, it is mainly distributed in Guangdong, Guangxi, Fujian, Taiwan, Hainan, Yunnan, Guizhou, Sichuan, Zhejiang, Hunan, Jiangxi and other provinces. In South Africa, India and Southeast Asian countries, the disease was once called Greening. In 1995, at the 13th International Conference of Citrus Virologists, it was unanimously approved to use Citrus HuangLongbing as the correct name for this kind of disease. The disease is extremely harmful to citrus production, and susceptible citrus varieties may lose their ability to bear fruit within 3 to 5 years, or even die. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
Inventor 邓小玲黄光得梅慧兰黎智龙
Owner SOUTH CHINA AGRI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products